Voyage AI Rerank 2.5
First reranker with instruction-following capabilities enabling dynamic query steering and domain-specific optimization. Supports 32K token context (8x Cohere's) through advanced distillation techniques.
Model Information
- Provider
- Voyage AI
- License
- Proprietary
- Price per 1M tokens
- $0.050
- Release Date
- 2025-08-11
- Model Name
- voyage-rerank-2.5
- Total Evaluations
- 2100
Performance Record
Wins1314 (62.6%)
Losses692 (33.0%)
Ties94 (4.5%)
Wins
Losses
Ties
Performance Overview
ELO ratings by dataset
Voyage AI Rerank 2.5's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.
Voyage AI Rerank 2.5 - ELO by Dataset
Detailed Metrics
Dataset breakdown
Performance metrics across different benchmark datasets, including accuracy and latency percentiles.
SciFact
ELO 164467.7% WR237W-107L-6T
Accuracy Metrics
- nDCG@5
- 0.865
- nDCG@10
- 0.882
- Recall@5
- 0.892
- Recall@10
- 0.940
Latency Distribution
- Mean
- 667ms
- P50 (Median)
- 621ms
- P90
- 819ms
DBPedia
ELO 163466.6% WR233W-111L-6T
Accuracy Metrics
- nDCG@5
- 0.657
- nDCG@10
- 0.744
- Recall@5
- 0.062
- Recall@10
- 0.110
Latency Distribution
- Mean
- 571ms
- P50 (Median)
- 610ms
- P90
- 734ms
FiQa
ELO 162669.1% WR242W-95L-13T
Accuracy Metrics
- nDCG@5
- 0.108
- nDCG@10
- 0.119
- Recall@5
- 0.098
- Recall@10
- 0.128
Latency Distribution
- Mean
- 540ms
- P50 (Median)
- 564ms
- P90
- 626ms
MSMARCO
ELO 154749.1% WR172W-118L-60T
Accuracy Metrics
- nDCG@5
- 0.971
- nDCG@10
- 0.974
- Recall@5
- 0.993
- Recall@10
- 1.000
Latency Distribution
- Mean
- 583ms
- P50 (Median)
- 611ms
- P90
- 630ms
business reports
ELO 154460.3% WR211W-130L-9T
Latency Distribution
- Mean
- 714ms
- P50 (Median)
- 617ms
- P90
- 834ms
PG
ELO 151662.6% WR219W-131L-0T
Latency Distribution
- Mean
- 588ms
- P50 (Median)
- 611ms
- P90
- 746ms
Compare Models
See how it stacks up
Compare Voyage AI Rerank 2.5 with other top rerankers to understand the differences in performance, accuracy, and latency.